CO 2 flooding is an efficient technique for enhancing oil recovery and carbon sequestration, where accurate estimation of the minimum miscibility pressure (MMP) is crucial. Conventional experiment and numerical simulations are time-cost and often inaccurate. Therefore, it is essential to develop an efficient and accurate model for MMP prediction. In this work, we introduced a genetic algorithm-optimized random forest (GA-RF) model using 260 samples with eight input features, including reservoir temperature (T R ), molecular weight of C 5+ pseudo-components (MWC 5+ ), ratio of the mole percent of volatile to intermediate fractions (vol./int.), and mole fractions of injected gas (CO 2 , H 2 S, CH 4 , C 2 -C 4 , and N 2 ). Four algorithms- random forest (RF), multilayer perceptron (MLP), support vector regression (SVR), and gradient boosting decision tree (GBDT) are compared. RF performs best and is further optimized by GA. The resulting GA-RF model outperforms traditional methods, with prediction accuracy of 0.99 and a root mean square error of 0.74. The model was applied to CO 2 -hydrocarbons system from different low-permeability reservoirs in China. Results show that the GA-RF model demonstrated an average relative error of 3.43%. These findings highlight that the GA-RF model has great potentials for predicting MMP during CO 2 flooding and improving CO 2 miscible flooding efficiency.
Zheng et al. (Thu,) studied this question.